AI Operations Engineer (RPA & Model Evaluation)

Handshake - Contract

November 2025 – June 2026

• Evaluated multimodal AI agents against structured rubrics to assess response quality, reasoning accuracy, and domain understanding across generalist tasks.
• Built AutoHandshake!, a Selenium-based RPA suite that eliminated 95% of manual annotation and triage effort across 400+ contractor hours with unattended execution, failure recovery, and full audit trails.
• Mentored contractors on platform operations, rubric interpretation, and efficient evaluation workflows.

Expert Contributor

Snorkel AI - Contract

December 2025 – June 2026

• Engineered constraint-based training workflows across 2 major contracted projects, training Claude and ChatGPT models on complex programming and logic tasks.
• Executed comprehensive CI/CD testing and validation protocols, ensuring robust deployment stability and training set quality.
• Designed rigorous evaluation frameworks to systematically assess model reasoning capabilities, driving continuous improvements in code generation and logical deduction accuracy.

Search Quality Evaluator

RWS Group - Contract

April 2025 – August 2025

• Assessed search relevance and LLM output quality against detailed rubrics across Google query simulations and third-party models, identifying failure patterns that informed ranking and UX improvements.

Freelance Software Engineer

July 2021 – Present

• Developed workflow automation tools and SDKs for web API integration and device I/O, eliminating repetitive manual processes for individual clients.
• Built an AI-assisted grading platform with LMS OAuth integration and automated rubric application, achieving ~95% accuracy in real-world classroom use and cutting instructor grading time by half.